Kannan Ramchandran

Communication-Efficient Gradient Coding for Straggler Mitigation in\n Distributed Learning

2020 · arXiv (Cornell University)

Distributed implementations of gradient-based methods, wherein a server\ndistributes gradient computations across worker machines, need to overcome two\nlimitations: delays caused by slow running machines called 'stragglers', and\ncommunication overheads. Recently, Ye and Abbe [ICML 2018] proposed a\ncoding-theoretic …

Spectral Regularization Allows Data-frugal Learning over Combinatorial Spaces

2022 · arXiv (Cornell University)

Data-driven machine learning models are being increasingly employed in several important inference problems in biology, chemistry, and physics which require learning over combinatorial spaces. Recent empirical evidence (see, e.g., [1], [2], [3]) suggests that regularizing …

The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learning

2023 · arXiv (Cornell University)

Modern data aggregation often involves a platform collecting data from a network of users with various privacy options. Platforms must solve the problem of how to allocate incentives to users to convince them to share …